ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-27 16:44:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enable MLA-3 in crippled GGUFs: WIP

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-05-11 14:18:24 +03:00
parent 504fb890d9
commit 8ee5008f7e
3 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.cpp
View File

@@ -2319,6 +2319,7 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params &
if (params.n_gpu_layers != -1) {
mparams.n_gpu_layers = params.n_gpu_layers;
}
mparams.mla = params.mla_attn;
mparams.rpc_servers = params.rpc_servers.c_str();
mparams.main_gpu = params.main_gpu;
mparams.split_mode = params.split_mode;